FreeU - ComfyUI Built-in Node Documentation

The FreeU node applies frequency-domain modifications to a model’s output blocks to enhance image generation quality.

The FreeU node applies frequency-domain modifications to a model’s output blocks to enhance image generation quality. It works by scaling different channel groups and applying Fourier filtering to specific feature maps, allowing for fine-tuned control over the model’s behavior during the generation process.

Inputs

Parameter	Description	Data Type	Required	Range
model	The model to apply FreeU modifications to	MODEL	Yes	-
b1	Backbone scaling factor applied to feature maps with model_channels × 4 channels (default: 1.1). Marked as an advanced setting.	FLOAT	Yes	0.0 - 10.0
b2	Backbone scaling factor applied to feature maps with model_channels × 2 channels (default: 1.2). Marked as an advanced setting.	FLOAT	Yes	0.0 - 10.0
s1	Skip connection scaling factor applied to feature maps with model_channels × 4 channels (default: 0.9). Marked as an advanced setting.	FLOAT	Yes	0.0 - 10.0
s2	Skip connection scaling factor applied to feature maps with model_channels × 2 channels (default: 0.2). Marked as an advanced setting.	FLOAT	Yes	0.0 - 10.0

Note: FreeU adjustments are applied only to feature maps whose channel count equals model_channels × 4 (using b1 and s1) or model_channels × 2 (using b2 and s2). The Fourier filter scales only the central low-frequency region (threshold of 1) of the skip connection feature maps; all other frequency components remain unchanged. All four scaling parameters accept values between 0.0 and 10.0 in steps of 0.01.

Outputs

Output Name	Description	Data Type
model	The modified model with FreeU patches applied	MODEL

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 7f7bd34964218ed16c9e58caa446d0c1e69f116607334df4a114cdc4adaf047f